Pdf4Vllm
by pyjudgecommunityv1.0.2
PDF reading MCP server optimized for vision LLMs that automatically detects text corruption and switches to image extraction while preserving reading order.
From the registry: PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
Install & configure
Prerequisites
- requiredPython 3.10+Python runtime required
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `pdf4vllm` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.10+** — Python runtime required
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["pdf4vllm-mcp"]
- optional environment variables:
- `PDF_MAX_PAGES`: Max pages per request (default: 10) (example: `20`)
- `PDF_PAGE_IMAGE_DPI`: DPI for page image rendering (default: 100) (example: `150`)
Note: PDF reading optimized for vision LLMs. Auto-detects text corruption and switches to image rendering. Supports grep_pdf tool if pdfgrep is installed.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: PDF reading optimized for vision LLMs. Auto-detects text corruption and switches to image rendering. Supports grep_pdf tool if pdfgrep is installed.
Tools (3)
list_pdfs
Find PDF files with glob filtering (`name_pattern`).
read_pdf
Extract PDF content as ordered blocks.
grep_pdf
Search text in PDFs using pdfgrep (requires `pdfgrep` installed).
Environment variables
PDF_MAX_PAGESrequiredMaximum number of pages to process per request.PDF_PAGE_IMAGE_DPIrequiredDPI for rendering page images.Prerequisites
- • Python 3.10+
Packages
pdf4vllm-mcp
pypiv1.0.2transport: stdio
Details
- Language
- Python
- License
- NOASSERTION
- Released
- Dec 2, 2025
- Last commit
- Jan 12, 2026
- Registry name
- io.github.PyJudge/pdf4vllm